Abstract
This research work focus on the latest studies that have used Machine learning to find a solution of sentiment analysis problems related to sentiment polarization. In preprocessing steps, the Models applied stop words and Bag of Words to a collection of datasets. Even with the widespread usage and acceptance of some approaches, a superior technique for categorizing the polarization of a text documents is tough to make out. Machine learning has lately evoked the attention as a method for sentiment investigation. The present work proposes a machine learning based hybrid algorithm that incorporate N-gram technique as a feature extraction and combines Decision tree classifier and Random forest Classifier techniques as a classification for sentiment analysis. Naïve bayse, linear classifier and support vector machine approaches are perform in the perspective of sentiment classification. Finally, a comparative study with the different supervised algorithm is implemented on product reviews dataset. The performance of models are evaluated on confusion matrix. In the comparative analysis of classification techniques, the combined technique has shown better results than previously used supervised techniques of naïve bayse ,linear classifier and support vector machine.
Key-Words / Index Term
sentiment analysis; Machine Learning; Opinion Mining; Sentiment classification; feature selection; Natural Language Processing; support vector machine
References
[1]. Mohammad S, Dunne C, Dorr B., “Generating high-coverage semantic orientation lexicons from overly marked words and a thesaurus,” In: Proceedings of the conference on Empirical Methods in Natural Language Processing (EMNLP’09); 2009
[2]. Melville, Wojciech Gryc, “Sentiment Analysis of Blogs by Combining Lexical Knowledge with Text Classification”, KDD?09, June 28–July 1, 2009, Paris, France. Copyright 2009 ACM 978-1-60558-495-9/09/06.
[3]. Qiang Ye, Ziqiong Zhang, Rob Law, “Sentiment classification of online reviews to travel destinations by supervised machine learning approaches”, Expert Systems with Applications Vol.36, pp.6527–6535, 2009.
[4]. Gang Li and Fei Liu, "A clustering-based approach on sentiment analysis," 2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering, pp. 331-337, 2010.
[5]. Khairullah Khan, Baharum B. Baharudin, Aurangzeb Khan, and Fazal_e_Malik, “Automatic Extraction of Features and Opinion Oriented Sentences from Customer Reviews”, World Academy of Science, Engineering and Technology, Vol.62, 2010.
[6]. Doaa Mohey El-Din Mohamed Hussein, “A survey on sentiment analysis challenges,” Journal of King Saud University – Engineering Sciences, Vol.30, pp.330–338, 2018.
[7]. Wang G, Sun J, Ma J, Xu K, Gu J (2014), “Sentiment classification: the contribution of ensemble learning,” Decis Support Syst, Vol.57, pp.77–93, 2014.
[8]. Alexander Ligthart at.al., “Systematic reviews in sentiment analysis: a tertiary study. Artif Intell Rev, Vol.54, pp4997–5053, 2021.
[9]. Hemmatian F, Sohrabi MK, “A survey on classification techniques for opinion mining and sentiment analysis,” Artif Intell Rev., Vol.52, Issue.3, pp.1495–1545, 2017.
[10]. Wu C. at. al., “Semi-supervised dimensional sentiment analysis with variational autoencoder,” Knowl-Based Syst 165:30–39
[11]. Xu W, Tan Y, “Semi-supervised target-oriented sentiment classification,” Neurocomputing, Vol.337, pp.120–128, 2019.
[12]. Xu G, Meng Y, Qiu X, Yu Z, Wu X, “Sentiment analysis of comment texts based on BiLSTM”, IEEE Access, Vol.7, pp. 51522–51532, 2019.
[13]. Majumder N, Poria S, Peng H, Chhaya N, Cambria E, Gelbukh A, “Sentiment and sarcasm classification with multitask learning,” IEEE Intell Syst, Vol.34, issuen.3, pp.38–43, 2019.
